audit_site

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description carries the full burden. It discloses recursive behavior and the return of per-file scores, aggregate summary, and top opportunities. It does not mention authentication needs or rate limits, but the read-only nature is implied. Overall, it gives sufficient behavioral context for the agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only three sentences, each adding value: scope, return values, and use case. No unnecessary words; it is concise and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema, the description need not detail return values, but it still gives a high-level summary. It covers purpose, behavior, and usage context completely for an agent to decide when to invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It implicitly explains the 'folder' and 'pattern' parameters by stating 'every HTML file under a folder,' but the 'limit' parameter is not mentioned. Thus, it adds some meaning but not complete compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool recursively audits every HTML file under a folder, distinguishing it from audit_page (single page) and other sibling tools. The verb 'audit' and resource 'every HTML file under a folder' are specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly notes 'Useful as the first call against a content directory to spot the worst offenders quickly,' providing clear when-to-use guidance. While it does not explicitly say when not to use it, the sibling context implies using audit_page for single pages.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.